Upload MistralForCausalLM
Browse files- config.json +6 -6
- generation_config.json +1 -1
- model-00001-of-00003.safetensors +2 -2
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +2 -2
- model.safetensors.index.json +1 -1
config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
-
"eos_token_id":
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
|
@@ -16,11 +16,11 @@
|
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
-
"rope_theta":
|
| 20 |
-
"sliding_window":
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.36.2",
|
| 24 |
-
"use_cache":
|
| 25 |
-
"vocab_size":
|
| 26 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 1000000.0,
|
| 20 |
+
"sliding_window": null,
|
| 21 |
"tie_word_embeddings": false,
|
| 22 |
"torch_dtype": "float16",
|
| 23 |
"transformers_version": "4.36.2",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
}
|
generation_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
-
"eos_token_id":
|
| 5 |
"transformers_version": "4.36.2"
|
| 6 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
"transformers_version": "4.36.2"
|
| 6 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:232cdf4aae35bb40ac42a0c50eeff90f1c0309529b2c37fd90ebe61165615292
|
| 3 |
+
size 4943162240
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999819232
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b64c3754f9e448fbc40c181eccf74c8c6d4aafcc4f32ff39c822985365932c2f
|
| 3 |
size 4999819232
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85df27705be672c0407338bf9fca1ec2bf3bec912580bc8fa936b3f4aab520ac
|
| 3 |
+
size 4540516256
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 14483464192
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"lm_head.weight": "model-00003-of-00003.safetensors",
|